A Two-Stage Beamforming Approach for Noise Reduction and Dereverberation

Habets, Emanuël A. P.; Benesty, Jacob

doi:10.1109/tasl.2013.2239292

Cited by 63 publications

(34 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This propagation results in a signal attenuation and spectral distortion, called reverberation, that seriously degrades speech quality and intelligibility. Many dereverberation techniques have thus been proposed in the past (e.g., [1][2][3][4][5]). One direct way is to estimate an inverse filter of the room impulse response *Correspondence: mlyang@xidian.edu.cn 1 National Laboratory of Radar Signal Processing, Xidian University, Xi'an, China Full list of author information is available at the end of the article (RIR) [6] to deconvolve the reverberant signal.…”

Section: Introductionmentioning

confidence: 99%

A reverberation-time-aware DNN approach leveraging spatial information for microphone array dereverberation

Yang

Huang

et al. 2017

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

A reverberation-time-aware deep-neural-network (DNN)-based multi-channel speech dereverberation framework is proposed to handle a wide range of reverberation times (RT60s). There are three key steps in designing a robust system. First, to accomplish simultaneous speech dereverberation and beamforming, we propose a framework, namely DNNSpatial, by selectively concatenating log-power spectral (LPS) input features of reverberant speech from multiple microphones in an array and map them into the expected output LPS features of anechoic reference speech based on a single deep neural network (DNN). Next, the temporal auto-correlation function of received signals at different RT60s is investigated to show that RT60-dependent temporal-spatial contexts in feature selection are needed in the DNNSpatial training stage in order to optimize the system performance in diverse reverberant environments. Finally, the RT60 is estimated to select the proper temporal and spatial contexts before feeding the log-power spectrum features to the trained DNNs for speech dereverberation. The experimental evidence gathered in this study indicates that the proposed framework outperforms the state-of-the-art signal processing dereverberation algorithm weighted prediction error (WPE) and conventional DNNSpatial systems without taking the reverberation time into account, even for extremely weak and severe reverberant conditions. The proposed technique generalizes well to unseen room size, array geometry and loudspeaker position, and is robust to reverberation time estimation error.

show abstract

Section: Introductionmentioning

confidence: 99%

A reverberation-time-aware DNN approach leveraging spatial information for microphone array dereverberation

Yang

Huang

et al. 2017

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…As the reverberant speech signal consists of highly dependent distortions that are delayed versions of the signal itself, the adaptive beamformers may attenuate the direct-path speech signal while reducing reverberation. Very recently, a conjunction of DS beamformer and minimum variance distortionless response (MVDR) beamformer has shown favorable performance for speech enhancement in the room environment [13].…”

Section: Introductionmentioning

confidence: 99%

Speech dereverberation for enhancement and recognition using dynamic features constrained deep neural networks and feature adaptation

Xiao

Zhao

Nguyen

et al. 2016

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

This paper investigates deep neural networks (DNN) based on nonlinear feature mapping and statistical linear feature adaptation approaches for reducing reverberation in speech signals. In the nonlinear feature mapping approach, DNN is trained from parallel clean/distorted speech corpus to map reverberant and noisy speech coefficients (such as log magnitude spectrum) to the underlying clean speech coefficients. The constraint imposed by dynamic features (i.e., the time derivatives of the speech coefficients) are used to enhance the smoothness of predicted coefficient trajectories in two ways. One is to obtain the enhanced speech coefficients with a least square estimation from the coefficients and dynamic features predicted by DNN. The other is to incorporate the constraint of dynamic features directly into the DNN training process using a sequential cost function. In the linear feature adaptation approach, a sparse linear transform, called cross transform, is used to transform multiple frames of speech coefficients to a new feature space. The transform is estimated to maximize the likelihood of the transformed coefficients given a model of clean speech coefficients. Unlike the DNN approach, no parallel corpus is used and no assumption on distortion types is made. The two approaches are evaluated on the REVERB Challenge 2014 tasks. Both speech enhancement and automatic speech recognition (ASR) results show that the DNN-based mappings significantly reduce the reverberation in speech and improve both speech quality and ASR performance. For the speech enhancement task, the proposed dynamic feature constraint help to improve cepstral distance, frequency-weighted segmental signal-to-noise ratio (SNR), and log likelihood ratio metrics while moderately degrades the speech-to-reverberation modulation energy ratio. In addition, the cross transform feature adaptation improves the ASR performance significantly for clean-condition trained acoustic models.

show abstract

“…There are multiple methods of implementing beam formers such as delay-sum model [4][5] [5][6][7]. The objective of the work is to improve beam forming using simple and robust methods.…”

Section: Introductionmentioning

confidence: 99%

“…We aim to implement a two stage design consisting of a delay sum model and LMS onto a prototype board, FPGA. This two stage approach concentrates on de-reverberation by using signal independent beam former or a conventional beam former in the first stage and a signal dependent algorithm or an adaptive algorithm for noise reduction in the second stage [6].…”

Section: Introductionmentioning

confidence: 99%

Design and Analysis of Two Stage Model for Effective Beam forming using MATLAB and VerilogHDL

Sivaraman¹,

P.C²,

Sundaramoorthy³

et al. 2016

IJSIP

View full text Add to dashboard Cite

show abstract

A Two-Stage Beamforming Approach for Noise Reduction and Dereverberation

Cited by 63 publications

References 35 publications

A reverberation-time-aware DNN approach leveraging spatial information for microphone array dereverberation

A reverberation-time-aware DNN approach leveraging spatial information for microphone array dereverberation

Speech dereverberation for enhancement and recognition using dynamic features constrained deep neural networks and feature adaptation

Design and Analysis of Two Stage Model for Effective Beam forming using MATLAB and VerilogHDL

Contact Info

Product

Resources

About